feat: add kubernetes support

.github/workflows/integration-test.yml

@@ -89,7 +89,7 @@ jobs:
           POSTGRES_USER: root
           POSTGRES_PASSWORD: rootpassword
           POSTGRES_DB: nextcloud
-        options: --health-cmd pg_isready --health-interval 5s --health-timeout 2s --health-retries 5
+        options: --health-cmd pg_isready --health-interval 5s --health-timeout 2s --health-retries 5 --name postgres --hostname postgres
 
     steps:
       - name: Checkout server
@@ -120,6 +120,14 @@ jobs:
           path: context_chat_backend/
           persist-credentials: false
 
+      - name: Checkout app_api
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
+        with:
+          repository: nextcloud/app_api
+          ref: ${{ matrix.server-versions == 'master' && 'main' || matrix.server-versions }}
+          path: apps/app_api
+          persist-credentials: false
+
       - name: Get app version
         id: appinfo
         uses: skjnldsv/xpath-action@7e6a7c379d0e9abc8acaef43df403ab4fc4f770c # master
@@ -167,6 +175,10 @@ jobs:
           cd ..
           rm -rf documentation
 
+      - name: Run files scan
+        run: |
+          ./occ files:scan --all
+
       - name: Setup python 3.11
         uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5
         with:
@@ -195,42 +207,109 @@ jobs:
           timeout 10 ./occ app_api:daemon:register --net host manual_install "Manual Install" manual-install http localhost http://localhost:8080
           timeout 120 ./occ app_api:app:register context_chat_backend manual_install --json-info "{\"appid\":\"context_chat_backend\",\"name\":\"Context Chat Backend\",\"daemon_config_name\":\"manual_install\",\"version\":\"${{ fromJson(steps.appinfo.outputs.result).version }}\",\"secret\":\"12345\",\"port\":10034,\"scopes\":[],\"system_app\":0}" --force-scopes --wait-finish
           ls -la context_chat_backend/persistent_storage/*
-          sleep 30 # Wait for the em server to get ready
-
-      - name: Scan files, baseline
-        run: |
-          ./occ files:scan admin
-          ./occ context_chat:scan admin -m text/plain
 
-      - name: Check python memory usage
+      - name: Initial memory usage check
         run: |
           ps -p $(cat pid.txt) -o pid,cmd,%mem,rss --sort=-%mem
           ps -p $(cat pid.txt) -o %mem --no-headers > initial_mem.txt
 
-      - name: Scan files
+      - name: Run cron jobs
+        run: |
+          # every 10 seconds indefinitely
+          while true; do
+            php cron.php
+            sleep 10
+          done &
+          sleep 30
+          # list all the bg jobs
+          ./occ background-job:list
+
+      - name: Initial dump of DB with context_chat_queue populated
+        if: always()
         run: |
-          ./occ files:scan admin
-          ./occ context_chat:scan admin -m text/markdown &
-          ./occ context_chat:scan admin -m text/x-rst
+          docker exec postgres pg_dump nextcloud > /tmp/0_pgdump_nextcloud
 
-      - name: Check python memory usage
+      - name: Periodically check context_chat stats for 15 minutes to allow the backend to index the files
         run: |
-          ps -p $(cat pid.txt) -o pid,cmd,%mem,rss --sort=-%mem
-          ps -p $(cat pid.txt) -o %mem --no-headers > after_scan_mem.txt
+          success=0
+          echo "::group::Checking stats periodically for 15 minutes to allow the backend to index the files"
+          for i in {1..90}; do
+            echo "Checking stats, attempt $i..."
+
+            stats_err=$(mktemp)
+            stats_exit=0
+            stats=$(timeout 30 ./occ context_chat:stats --json 2>"$stats_err") || stats_exit=$?
+            echo "Stats output:"
+            echo "$stats"
+            if [ -s "$stats_err" ]; then
+              echo "Stderr:"
+              cat "$stats_err"
+            fi
+            echo "---"
+            rm -f "$stats_err"
+
+            # Check for critical errors in output
+            if [ $stats_exit -ne 0 ] || echo "$stats" | grep -q "Error during request"; then
+              echo "Backend connection error detected (exit=$stats_exit), retrying..."
+              sleep 10
+              continue
+            fi
+
+            # Extract total eligible files
+            total_eligible_files=$(echo "$stats" | jq '.eligible_files_count' || echo "")
+
+            # Extract indexed documents count (files__default)
+            indexed_count=$(echo "$stats" | jq '.vectordb_document_counts.files__default' || echo "")
+
+            echo "Total eligible files: $total_eligible_files"
+            echo "Indexed documents (files__default): $indexed_count"
+
+            diff=$((total_eligible_files - indexed_count))
+            threshold=$((total_eligible_files * 3 / 100))
+
+            # Check if difference is within tolerance
+            if [ $diff -le $threshold ]; then
+              echo "Indexing within 3% tolerance (diff=$diff, threshold=$threshold)"
+              success=1
+              break
+            else
+              progress=$((diff * 100 / total_eligible_files))
+              echo "Outside 3% tolerance: diff=$diff (${progress}%), threshold=$threshold"
+            fi
+
+            # Check if backend is still alive
+            ccb_alive=$(ps -p $(cat pid.txt) -o cmd= | grep -c "main.py" || echo "0")
+            if [ "$ccb_alive" -eq 0 ]; then
+              echo "Error: Context Chat Backend process is not running. Exiting."
+              exit 1
+            fi
+
+            sleep 10
+          done
+
+          echo "::endgroup::"
+
+          if [ $success -ne 1 ]; then
+            echo "Max attempts reached"
+            exit 1
+          fi
 
       - name: Run the prompts
         run: |
           ./occ background-job:worker 'OC\TaskProcessing\SynchronousBackgroundJob' > worker1_logs 2>&1 &
           ./occ background-job:worker 'OC\TaskProcessing\SynchronousBackgroundJob' > worker2_logs 2>&1 &
 
+          echo ::group::English prompt
           OUT1=$(./occ context_chat:prompt admin "Which factors are taken into account for the Ethical AI Rating?")
           echo "$OUT1"
-          echo '--------------------------------------------------'
+          echo "$OUT1" | grep -q "If all of these points are met, we give a Green label." || exit 1
+          echo ::endgroup::
+
+          echo ::group::German prompt
           OUT2=$(./occ context_chat:prompt admin "Welche Faktoren beeinflussen das Ethical AI Rating?")
           echo "$OUT2"
-
-          echo "$OUT1" | grep -q "If all of these points are met, we give a Green label." || exit 1
           echo "$OUT2" | grep -q "If all of these points are met, we give a Green label." || exit 1
+          echo ::endgroup::
 
       - name: Check python memory usage
         run: |
@@ -250,18 +329,10 @@ jobs:
             echo "Memory usage during scan is stable. No memory leak detected."
           fi
 
-      - name: Compare memory usage and detect leak
+      - name: Final dump of DB with vectordb populated
+        if: always()
         run: |
-          initial_mem=$(cat after_scan_mem.txt | tr -d ' ')
-          final_mem=$(cat after_prompt_mem.txt | tr -d ' ')
-          echo "Initial Memory Usage: $initial_mem%"
-          echo "Memory Usage after prompt: $final_mem%"
-
-          if (( $(echo "$final_mem > $initial_mem" | bc -l) )); then
-            echo "Memory usage has increased during prompt. Possible memory leak detected!"
-          else
-            echo "Memory usage during prompt is stable. No memory leak detected."
-          fi
+          docker exec postgres pg_dump nextcloud > /tmp/1_pgdump_nextcloud
 
       - name: Show server logs
         if: always()
@@ -298,6 +369,21 @@ jobs:
         run: |
           tail -v -n +1 context_chat_backend/persistent_storage/logs/em_server.log* || echo "No logs in logs directory"
 
+      - name: Upload database dumps
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: database-dumps-${{ matrix.server-versions }}-php@${{ matrix.php-versions }}
+          path: |
+            /tmp/0_pgdump_nextcloud
+            /tmp/1_pgdump_nextcloud
+
+      - name: Final stats log
+        if: always()
+        run: |
+          ./occ context_chat:stats
+          ./occ context_chat:stats --json
+
   summary:
     permissions:
       contents: none